| { | |
| "best_metric": 0.34856516122817993, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6920415224913494, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01384083044982699, | |
| "grad_norm": 5.880698204040527, | |
| "learning_rate": 5e-05, | |
| "loss": 7.6368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01384083044982699, | |
| "eval_loss": 7.8842244148254395, | |
| "eval_runtime": 14.7958, | |
| "eval_samples_per_second": 32.915, | |
| "eval_steps_per_second": 4.123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02768166089965398, | |
| "grad_norm": 8.048609733581543, | |
| "learning_rate": 0.0001, | |
| "loss": 7.5947, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04152249134948097, | |
| "grad_norm": 5.903276443481445, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.4678, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05536332179930796, | |
| "grad_norm": 6.215991020202637, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.8011, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06920415224913495, | |
| "grad_norm": 6.165921211242676, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.753, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08304498269896193, | |
| "grad_norm": 7.031081676483154, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.7688, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09688581314878893, | |
| "grad_norm": 6.366204738616943, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.0197, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11072664359861592, | |
| "grad_norm": 4.397291660308838, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.249, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1245674740484429, | |
| "grad_norm": 5.513636589050293, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.83, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1384083044982699, | |
| "grad_norm": 4.908700942993164, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.4178, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1522491349480969, | |
| "grad_norm": 6.022943019866943, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.1281, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16608996539792387, | |
| "grad_norm": 3.7920618057250977, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.5878, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17993079584775087, | |
| "grad_norm": 3.0949554443359375, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5057, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19377162629757785, | |
| "grad_norm": 3.586160182952881, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0358, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20761245674740483, | |
| "grad_norm": 3.107851982116699, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8187, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22145328719723184, | |
| "grad_norm": 2.730515956878662, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7116, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.947086215019226, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6138, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2491349480968858, | |
| "grad_norm": 2.442556142807007, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5869, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2629757785467128, | |
| "grad_norm": 2.137789726257324, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6223, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2768166089965398, | |
| "grad_norm": 1.5641061067581177, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4856, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2906574394463668, | |
| "grad_norm": 1.357182264328003, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4392, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3044982698961938, | |
| "grad_norm": 1.2531371116638184, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4463, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.31833910034602075, | |
| "grad_norm": 1.172152042388916, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4772, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.33217993079584773, | |
| "grad_norm": 1.490871787071228, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4693, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3460207612456747, | |
| "grad_norm": 1.3255620002746582, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.55, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3460207612456747, | |
| "eval_loss": 0.43850070238113403, | |
| "eval_runtime": 14.6517, | |
| "eval_samples_per_second": 33.238, | |
| "eval_steps_per_second": 4.163, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35986159169550175, | |
| "grad_norm": 1.6745163202285767, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4418, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3737024221453287, | |
| "grad_norm": 1.39356529712677, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4356, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3875432525951557, | |
| "grad_norm": 1.2509773969650269, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4156, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4013840830449827, | |
| "grad_norm": 1.373849630355835, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4337, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41522491349480967, | |
| "grad_norm": 1.3212683200836182, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3954, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4290657439446367, | |
| "grad_norm": 1.1807379722595215, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3588, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4429065743944637, | |
| "grad_norm": 1.229190468788147, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4015, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.45674740484429066, | |
| "grad_norm": 1.209175705909729, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4033, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.2595385313034058, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3348, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4844290657439446, | |
| "grad_norm": 1.014263391494751, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.339, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4982698961937716, | |
| "grad_norm": 1.1709855794906616, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3825, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5121107266435986, | |
| "grad_norm": 1.6771941184997559, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4577, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5259515570934256, | |
| "grad_norm": 2.0534322261810303, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5409, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5397923875432526, | |
| "grad_norm": 2.5196380615234375, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3799, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5536332179930796, | |
| "grad_norm": 1.5649428367614746, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3562, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5674740484429066, | |
| "grad_norm": 1.1818357706069946, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3894, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5813148788927336, | |
| "grad_norm": 1.0383087396621704, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3347, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5951557093425606, | |
| "grad_norm": 1.0444445610046387, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.3088, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6089965397923875, | |
| "grad_norm": 1.0008732080459595, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3268, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6228373702422145, | |
| "grad_norm": 0.9677495360374451, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.35, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6366782006920415, | |
| "grad_norm": 0.7487701773643494, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3004, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6505190311418685, | |
| "grad_norm": 1.0909370183944702, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3704, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6643598615916955, | |
| "grad_norm": 1.1073919534683228, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3738, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6782006920415224, | |
| "grad_norm": 1.126089096069336, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3754, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6920415224913494, | |
| "grad_norm": 1.246249794960022, | |
| "learning_rate": 0.0, | |
| "loss": 0.4443, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6920415224913494, | |
| "eval_loss": 0.34856516122817993, | |
| "eval_runtime": 14.6363, | |
| "eval_samples_per_second": 33.273, | |
| "eval_steps_per_second": 4.168, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.988598893678428e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |